3 people 1206891822 [ROCm][KVConnector][MoRI-IO] Fix WRITE-mode remote-TP rank collapse (#46332 follow-up) (#47764) ...

Signed-off-by: avininjamay8 <avininjamay8@users.noreply.github.com>
Signed-off-by: avininjamay8 <Avinash.Paul@amd.com>
Co-authored-by: avininjamay8 <avininjamay8@users.noreply.github.com>
Co-authored-by: avininjamay8 <avpaul@amd.com>

2026-07-27 20:26:24 -05:00

..

device_communicators

[Core] Fail fast when /dev/shm is too small for the shm ring buffer (#48879)

2026-07-27 19:48:35 +00:00

ec_transfer

[EC Connector] CPU Offloading EC Connector (#47423)

2026-07-13 20:09:41 +03:00

elastic_ep

[EPLB] Mask padding in EPLB load recording (#38128)

2026-06-28 19:43:58 -07:00

eplb

[AMD][Bugfix][EPLB] Fix elastic EP scaling accuracy on ROCm (#47206)

2026-07-24 13:35:27 -07:00

kv_transfer

[ROCm][KVConnector][MoRI-IO] Fix WRITE-mode remote-TP rank collapse (#46332 follow-up) (#47764)

2026-07-27 20:26:24 -05:00

weight_transfer

[Bugfix][SpecDecode] Scope MTP completeness checks outside bucketed updates (#49178)

2026-07-21 18:56:39 -07:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

communication_op.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

kv_events.py

[KV Offloading] Per-request tier filtering with TierFilter/TierMatcher (#48123)

2026-07-27 13:29:57 +03:00

nixl_utils.py

[ROCm] Upgrade NIXL and UCX (#49251)

2026-07-21 22:30:02 -05:00

parallel_state.py

[Core][Distributed] Add process-checkpoint lifecycle hooks for communicators (starting with Flashinfer) (#46877)

2026-07-26 14:47:50 -04:00

stateless_coordinator.py

Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

2026-06-20 13:38:10 -07:00

utils.py

fix(distributed): propagate distributed_timeout_seconds to NCCL device groups (#45159)

2026-07-07 02:52:51 +00:00